README.md

metadata

library_name: stable-baselines3
tags:
  - Pendulum-v1
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - metrics:
          - type: mean_reward
            value: '-272.21 +/- 159.73'
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Pendulum-v1
          type: Pendulum-v1

PPO Agent playing Pendulum-v1

This is a trained model of a PPO agent playing Pendulum-v1 using the stable-baselines3 library.

Usage (with Stable-baselines3)

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env

# Create the environment
env_id = "Pendulum-v1"
env = make_vec_env(env_id, n_envs=1)

# Instantiate the agent
model = PPO(
    "MlpPolicy",
    env,
    gamma=0.98,
    use_sde=True,
    sde_sample_freq=4,
    learning_rate=1e-3,
    verbose=1,
)

# Train the agent
model.learn(total_timesteps=int(1e5))